Gluster users - Aug 2015 - Arbiter volume

?Hi,



Gave arbiter volume a shot today but ran into som problems with it:



1. My arbiter brick is running with a much smaller disk which during a
"df" presents a problem, it shows the smaller disksize. If I
understand the arbiter correctly, then there is no need to match the size of the
"real" bricks, so is this by design?



2. Using libgfapi with qemu libvirt did not work for me, it just hangs with high
cpuload on libvirtd. Should this work?



Running Centos 7 (qemu libvirt) and FreeBSD 10.1 (as arbiter) with gluster
3.7.2.


Fredrik Brandt

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://www.gluster.org/pipermail/gluster-users/attachments/20150805/e5c3721d/attachment.html>

On 08/06/2015 02:41 AM, Fredrik Brandt wrote:
> Arbiter volume
>
> ???Hi,
>
>
> Gave arbiter volume a shot today but ran into som problems with it:
>
>
> 1. My arbiter brick is running with a much smaller disk which during a 
> "df" presents a problem, it shows the smaller disksize. If I 
> understand the arbiter correctly, then there is no need to match the 
> size of the "real" bricks, so is this by design?
>
Good point, I think for statfs i.e. syscall used by 'df' we need to 
ignore the output from arbiter brick. Thanks for this input. We will 
raise a bug and work on it. You shouldn't see any problems because of 
this issue though.
>
>
> 2. Using libgfapi with qemu libvirt did not work for me, it just hangs 
> with high cpuload on libvirtd. Should this work?
>
Just to isolate the problem does it work if you try to use the VMs 
through fuse mount?
>
>
> Running Centos 7 (qemu libvirt) and FreeBSD 10.1 (as arbiter) with 
> gluster 3.7.2.
>
Could you give all the logs in /var/log/glusterfs and also the libvirtd 
logs.
>
>
> Fredrik Brandt
>
>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://www.gluster.org/mailman/listinfo/gluster-users
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://www.gluster.org/pipermail/gluster-users/attachments/20150806/673eb1a8/attachment.html>

Hoping someone can help.

If I have a brick that was created on shared storage (dual-host jbod, 
for example), and the node on which that brick was created/mounted goes 
down, can I "transparently" mount the brick from another node and have
things behave the same (i.e glusterfs recognizes the brick as being the 
same regardless of which nodes it joins the quorum)?

If so, what would I need to do to enable that behavior?

thanks,
-john c.